Max Robotics — Global Service Robot Directory + US Certification

About

Zihao Sun is a robotics researcher whose work lies at the intersection of autonomous navigation and intelligent manipulation, with a particular focus on deep reinforcement learning (DRL) and self-supervised perception. His most cited paper, “Self-supervised learning of LiDAR odometry based on spherical projection” (2022, 8 citations), introduces a novel approach that eliminates the need for costly ground-truth pose labels, enabling mobile robots to learn robust localization from raw sensor data—a critical step toward scalable autonomy in real-world environments. In the domain of robotic manipulation, Sun has made significant contributions to hierarchical and goal-conditioned reinforcement learning. His 2025 paper on “Hierarchical reinforcement learning with curriculum demonstrations and goal-guided policies” (4 citations) addresses the challenge of long-horizon sequential tasks, while his 2024 work on “Goal-Conditioned Reinforcement Learning With Adaptive Intrinsic Curiosity” (3 citations) tackles the exploration-exploitation dilemma in sparse-reward settings. Sun’s research on peg-in-hole assembly tasks (2024, 2 citations) further demonstrates his commitment to bridging simulation and real-world industrial applications. With a growing citation footprint and a focus on learning efficiency, Sun is emerging as a promising voice in the next generation of robot learning researchers.